Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ORTH
    -0.06
    ;
    -0.06
    _TRA
    -0.06
    pst
    -0.06
    	pt
    -0.06
     gui
    -0.06
    _)↵
    -0.06
    ';
    -0.06
     looming
    -0.06
    ::-
    -0.06
    POSITIVE LOGITS
     ماك
    0.07
     Kraj
    0.07
    _contacts
    0.07
     Sponsored
    0.07
     Paolo
    0.06
     thermostat
    0.06
     Machinery
    0.06
    _ACC
    0.06
     Awakening
    0.06
    .cell
    0.06
    Act Density 0.003%

    No Known Activations